patient - Story 102658 | Emotion Vectors in Gemma4-31B

The train rumbled along the tracks, a rhythmic pulse that lulled Marcus into a state of semi-consciousness. He was engrossed in a particularly challenging puzzle book. His phone vibrated. A text. "Dinner at six? Can't wait!" The sender was "Liam". Marcus smiled, and leaned back, a very slight stretch in his posture. He was not planning on going anywhere. He closed his eyes. The train car swayed gently, and he imagined an empty table and all of the time in the world. He allowed the rocking of the train to fully overtake him. He would see about that when he woke.

Emotion: patient

Cluster: Passivity

PC1 (Valence): 2.71 Positive

PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion patient. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 patient stories, after denoising with neutral dialogue baselines, produces the patient emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the patient vector is projected through the unembedding matrix.

Promoted:

`rest`	0.467
`eventually`	0.415
`leisurely`	0.369
`慢慢`	0.357
`a`	0.355

Suppressed:

`无法`	-0.432
`even`	-0.428
`인해`	-0.421
`無法`	-0.415
`😣`	-0.391